Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2802 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.3174. Min Act: -0.0000

Data Index: 692092 (The Pile)

Max Activating Token Index: 174

Text #1

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2646. Min Act: -0.0000

Data Index: 885410 (The Pile)

Max Activating Token Index: 778

Text #2

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2821. Min Act: -0.0000

Data Index: 920365 (The Pile)

Max Activating Token Index: 71

Text #3

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1581492 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1511086 (The Pile)

Max Activating Token Index: 387

Text #5

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1810825 (The Pile)

Max Activating Token Index: 164

Text #6

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2620. Min Act: -0.0000

Data Index: 762087 (The Pile)

Max Activating Token Index: 156

Text #7

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2624. Min Act: -0.0000

Data Index: 218300 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2585. Min Act: -0.0000

Data Index: 629505 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1905649 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1240271 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2498. Min Act: -0.0000

Data Index: 630796 (The Pile)

Max Activating Token Index: 613

Text #12

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1746440 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2484. Min Act: -0.0000

Data Index: 295811 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1388535 (The Pile)

Max Activating Token Index: 686

Text #15

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2540. Min Act: -0.0000

Data Index: 589638 (The Pile)

Max Activating Token Index: 420

Text #16

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1693856 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2528. Min Act: -0.0000

Data Index: 722699 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1736105 (The Pile)

Max Activating Token Index: 479

Text #19

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2512. Min Act: -0.0000

Data Index: 551926 (The Pile)

Max Activating Token Index: 336